PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Class-Specific Hough Forests for Object Detection
Juergen Gall and Victor Lempitsky
IEEE Conf. on Computer Vision and Pattern Recognition 2009.

Abstract

We present a method for the detection of instances of an object class, such as cars or pedestrians, in natural images. Similarly to some previous works, this is accomplished via generalized Hough transform, where the detections of individual object parts cast probabilistic votes for possible locations of the centroid of the whole object; the detection hypotheses then correspond to the maxima of the Hough image that accumulates the votes from all parts. However, whereas the previous methods detect object parts using generative codebooks of part appearances, we take a more discriminative approach to object part detection. Towards this end, we train a class-specific Hough forest, which is a random forest that directly maps the image patch appearance to the probabilistic vote about the possible location of the object centroid. We demonstrate that Hough forests improve the results of the Hough-transform object detection significantly and achieve state-of-the-art performance for several classes and datasets.

EPrint Type:Article
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Machine Vision
ID Code:6438
Deposited By:Victor Lempitsky
Deposited On:08 March 2010